Induction of Finite-State Languages Using Second-Order Recurrent Networks
- 1 May 1992
- journal article
- Published by MIT Press in Neural Computation
- Vol. 4 (3) , 406-414
- https://doi.org/10.1162/neco.1992.4.3.406
Abstract
Second-order recurrent networks that recognize simple finite state languages over {0,1}* are induced from positive and negative examples. Using the complete gradient of the recurrent network and sufficient training examples to constrain the definition of the language to be induced, solutions are obtained that correctly recognize strings of arbitrary length.Keywords
This publication has 2 references indexed in Scilit:
- Finding structure in timeCognitive Science, 1990
- Finite State Automata and Simple Recurrent NetworksNeural Computation, 1989